Journal
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
Volume 18, Issue 3, Pages 1873-1882Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TII.2020.3044310
Keywords
Electroencephalography; Task analysis; Feature extraction; Brain modeling; Training; Frequency modulation; Informatics; Brain-computer interface (BCI); deep learning; electroencephalogram (EEG); motor imagery; reinforcement learning (RL); subject independent
Categories
Funding
- Institute for Information & Communications Technology Promotion (IITP) - Korea government [2017-0-00451, 2019-0-00079]
Ask authors/readers for more resources
In this article, a novel reinforcement-learning mechanism is proposed to select task-relevant temporal signal segments from a single EEG trial, combined with existing deep-learning-based methods. With experiments and validation, the proposed method showed significant improvements in intention identification performance.
In this article, we formulate the problem of estimating and selecting task-relevant temporal signal segments from a single electroencephalogram (EEG) trial in the form of a Markov decision process and propose a novel reinforcement-learning mechanism that can be combined with the existing deep-learning-based brain-computer interface methods. To be specific, we devise an actor-critic network such that an agent can determine which timepoints need to be used (informative) or discarded (uninformative) in composing the intention-related features in a given trial, and thus enhancing the intention identification performance. To validate the effectiveness of our proposed method, we conduct experiments with a publicly available big motor imagery (MI) dataset and apply our novel mechanism to various recent deep-learning architectures designed for MI classification. Based on the exhaustive experiments, we observe that our proposed method helped achieve statistically significant improvements in performance.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available